Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ZJU-REAL/Easelnpx agentmods add skills/zju-real/easel/copywritingWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zju-real/easel/copywriting)<a href="https://agentmods.dev/skills/zju-real/easel/copywriting"><img src="https://agentmods.dev/badge/skills/zju-real/easel/copywriting/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zju-real/easel/copywriting"><img src="https://agentmods.dev/badge/skills/zju-real/easel/copywriting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00115 | $0.02060 |
| Opus 5 | $0.00057 | $0.01030 |
| Sonnet 5 | $0.00023 | $0.00412 |
| Haiku 4.5 | $0.00012 | $0.00206 |
Grade A, and why
copywriting scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
营销文案写作
为国内营销场景撰写和优化高转化文案：种草、信息流广告、卖点提炼、活动促销、电商详情页、落地页。套经典框架，落国内语境。
职责边界
| 场景 | 交给谁 | 为什么 |
|---|---|---|
| 卖货/转化导向的营销文案（种草卖点、信息流广告、活动、详情页、落地页） | 本 SKILL | 以"促成购买/转化"为目标，讲卖点、讲收益、给 CTA |
| 整套小红书笔记（多卡片 + caption + hashtags + 去 AI + 校验全流程） | xhs-note-creator |
小红书图文/种草的总入口，不是单条文案 |
| 通用社媒内容（多平台原生格式、钩子、标签、互动引导） | social-content |
偏内容运营/涨粉互动，不强转化 |
| 严格套 PAS/AIDA/BAB/STAR 框架的结构化帖子（200-250 字、移动端排版） | post-formatter |
专做单一框架的规范化帖子 |
一句话分工：要卖货找 copywriting，要整套小红书笔记找 xhs-note-creator，要涨粉找 social-content，要套固定框架排版找 post-formatter。 可串联（本 SKILL 出卖点文案 → post-formatter 排成帖子 → social-content 适配多平台）。
输入
用户 prompt 中提供以下信息（缺失时主动询问）：
- 文案类型 — 种草 / 信息流广告 / 卖点提炼 / 活动促销 / 详情页 / 落地页
- 产品/服务 — 卖什么、核心卖点、与竞品的差异、能带来的结果
- 目标动作 — 希望用户做什么（下单、领券、加购、点击链接、私信咨询、到店）
- 投放场景/平台 — 小红书 / 抖音信息流 / 朋友圈广告 / 电商平台 / 落地页等（影响长度、语气、CTA 形式）
- 证据素材（如有）— 销量、评价、成分/参数、案例、资质
- 受众 — 谁看、什么消费顾虑
输出
按文案类型交付对应结构（详见 references/copy-frameworks.md），通常包含：
- 主标题/开头钩子 + 2-3 个备选
- 正文（按所选框架组织：痛点→方案→卖点→信任→CTA 等）
- 卖点清单（FAB：功能→优势→利益，逐条）
- CTA/行动引导 + 2-3 个备选
- 关键元素标注：说明选择理由和所用框架/原则
执行步骤
- 收集上下文 — 确认文案类型、产品卖点、目标动作、投放场景、受众、证据；缺失项主动询问。
- 确定语气 — 按 Profile 或用户指示定调（种草偏亲切真实、信息流偏直给、活动偏紧迫、详情页偏专业）。
- 提炼卖点 — 用 FAB 把产品特性翻译成用户利益（框架定义见
skills/shared/references/copy-frameworks.md），排出主次。 - 选框架搭结构 — 按内容目的从
skills/shared/references/copy-frameworks.md选框架（AIDA / PAS / FAB / 4U / BAB），再按文案类型从references/copy-frameworks.md取对应结构模板。 - 写标题/钩子 — 用
skills/shared/references/hook-title-formulas.md的标题/钩子公式产出 2-3 个备选。 - 填正文 — 逐段推进，一段一论点；用
references/natural-transitions.md保持衔接自然、口语流畅。 - 打磨风格 + 去 AI 门（强制） — 按
references/writing-style-rules.md抓营销文案特有的风格（讲利益、信任前置、反问/类比、CTA 给理由）；去 AI 味走 text-polisher 权威源并过门禁（../text-polisher/references/{phrases-to-remove,structures-to-avoid,zh-ai-markers}.md）——AI 味自检 ≥45/50、综合质量 ≥35/50，不达标先改再交付。本 SKILL 不维护去 AI 副本。 - 写 CTA — 按目标动作产出 2-3 个 CTA 备选。
- 字数校验（有长度约束的类型必做） — 信息流广告、详情页首屏、落地页等有字符/篇幅限制的，用脚本判定不靠肉眼数：
读python3 skills/shared/scripts/wordcount.py count -f outputs/主题名/copy.txtsocial_count与投放位的字符上限比对，超限交给text-condenser压缩后重数。 - 组装交付 — 按「输出」格式组装文案 + 标注 + 备选，写入
outputs/。
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 90 lines · 115 tokens per session scan A 603bd2e71cdf
copywriting is a skill published in the GitHub repository ZJU-REAL/Easel (710 stars, last pushed today), licensed Apache-2.0. It adds 115 tokens to every session and 2,060 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
skill-authoring
Author SKILL.md: frontmatter, structure, writing principles.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
roadtrip-navigator
Generate North American road-trip itineraries as a map-first, offline-friendly single-file HTML page. Plans around daily driving segments, overnight stops, fuel/EV-charging, national-park reservations (Recreation.gov / NPS), seasonal road closures, and timezone/border crossings — for executable, decision-ready trips.…
github-code-review
Review PRs: diffs, inline comments via gh or REST.
simplify-code
Sequential 3-lens cleanup of recent code changes.